Reinforcement Learning-Based Current Compensation for Brushless Doubly Fed Induction Generators Under Transient- and Low-Voltage Ride-Through Faults

Muhammad Ismail Marri, Najeeb Ur Rehman Malik, Muhammad Masud, Touqeer Ahmed Jumani (), Atta Ullah Khidrani and Zeeshan Shahid
Additional contact information
Muhammad Ismail Marri: Department of Electrical Engineering, DHA Suffa University, Karachi 75500, Pakistan
Najeeb Ur Rehman Malik: Department of Electrical Engineering, DHA Suffa University, Karachi 75500, Pakistan
Muhammad Masud: Department of Electrical Engineering, College of Engineering, University of Business and Technology, Jeddah 21361, Saudi Arabia
Touqeer Ahmed Jumani: Department of Electrical Engineering and Computer Science, College of Engineering, A’Sharqiyah University, Ibra 400, Oman
Atta Ullah Khidrani: Department of Electrical Engineering, Balochistan University of Engineering and Technology Khuzdar, Khuzdar 89100, Pakistan
Zeeshan Shahid: Department of Electrical Engineering, DHA Suffa University, Karachi 75500, Pakistan

Energies, 2025, vol. 18, issue 4, 1-26

Abstract: Wind and solar energy are increasingly vital for meeting clean renewable energy needs, with Brushless Doubly Fed Induction Generators gaining popularity due to their cost efficiency and reliability. A key challenge in integrating wind energy into the grid is ensuring low-voltage ride-through capability during faults and mitigating voltage fluctuations at the point of common coupling. Existing techniques, such as analytical models and evolutionary algorithms, aim to optimize reactive current compensation but suffer from low accuracy and high response times, respectively. This paper introduces a novel reinforcement learning-based current compensation technique for brushless doubly fed induction generators to address these limitations. The proposed reinforcement learning agent dynamically adjusts the reactive power to minimize voltage dips and stabilize the voltage profile during transient- and low-voltage ride-through faults, leveraging a reward function that penalizes deviations in voltage magnitude and increases in total harmonic distortion beyond 3%. By integrating reinforcement learning with traditional methods, the approach achieves faster and more adaptive compensation. Simulation results show that the reinforcement learning-based technique improves voltage recovery time by up to 50%, reduces total harmonic distortion by up to 44%, and minimizes current overshoot by up to 90% compared to state-of-the-art methods, enhancing the reliability and efficiency of wind energy systems.

Keywords: reinforcement learning; brushless doubly fed induction generator; low-voltage ride-through; transient (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/18/4/881/pdf (application/pdf)
https://www.mdpi.com/1996-1073/18/4/881/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:18:y:2025:i:4:p:881-:d:1589834

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().